[TIDL-7326] Improve documentation of TIDL-RT based inference with artifacts compiled with ONNX-RT

Signed-off-by: Abhay Chirania <a-chirania@ti.com>

Author: abhaychirania2411

examples/tidlrt_cpp/README.md

@@ -9,6 +9,10 @@
 
 ## Introduction
    - TIDL RT CPP APIs only supports the model inference for the models which can be fully offloaded to DSP. The user is expected  to run the [Python Examples](../osrt_python/README.md#python-example) on PC to generate the model artifacts.
+  - The model artifacts is expected to be generated with the following advanced options:
+    1. "advanced_options:add_data_convert_ops": 3
+  - For model compiled using ONNXRT, the order of outputs generated from TIDL-RT run can be obtained from 
+    `onnxrtMetaData.txt` file which can be found in the compiled model artifacts folder. The `outDataNames` defines the order of output.
 ## Setup
 - Prepare the Environment for the Model compilation by following the setup section [here](../../README.md#setup)